agentsclimarketplace

Review & quality

19,000 rows, by stacks then stars

1,766 of these skill files have been read, by 1,273 distinct authors, and what they tell an agent counted. What Review & quality authors agree on, and what they forbid

  • Create pr

    jae-labs/skills/skills/create-pr Skill

    0★ repo

    Inspects local git changes and generates a structured, high-quality PR description using the gh CLI. You MUST use this skill whenever the user asks to create a pull request, create a github pr, run '/create-pr', draft a PR description, summarize branch changes, review a diff before committing, or write a squash commit message. Even if the user only asks to "write a PR summary," invoke this skill to ensure proper branch hygiene and formatting.

  • Finishing a development branch

    jae-labs/skills/skills/finishing-a-development-branch Skill

    0★ repo

    Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

  • Grill me

    jae-labs/skills/skills/grill-me Skill

    0★ repo

    Stress-test a design or plan through relentless one-question-at-a-time interrogation. Walk down each branch of the decision tree, resolving dependencies one-by-one. Use when the user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

  • Principal sre reviewer

    jae-labs/skills/skills/principal-sre-reviewer Skill

    0★ repo

    Do not invoke automatically. Only run when the user explicitly requests the principal-sre-reviewer skill or asks to do a principal SRE review.

  • Receiving code review

    jae-labs/skills/skills/receiving-code-review Skill

    0★ repo

    Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

    The same file is in 28 other repositories

  • Requesting code review

    jae-labs/skills/skills/requesting-code-review Skill

    0★ repo

    Use when completing tasks, implementing major features, or before merging to verify work meets requirements

    The same file is in 11 other repositories

  • Thermo nuclear code quality review

    jae-labs/skills/skills/thermo-nuclear-code-quality-review Skill

    0★ repo

    Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.

    The same file is in 5 other repositories

  • Using git worktrees

    jae-labs/skills/skills/using-git-worktrees Skill

    0★ repo

    Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

    The same file is in 13 other repositories

  • Verification before completion

    jae-labs/skills/skills/verification-before-completion Skill

    0★ repo

    Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

    The same file is in 40 other repositories

  • Lowcode ai real chain runner

    xylvvv/agent-skills/skills/lowcode-ai-real-chain-runner Skill

    no license0★ repo

    Run lowcode-server persisted real-chain scripts with real providers, persist run records, verify MySQL records, write result JSON, and produce standardized reports. Use only for explicitly authorized regression, observation, or asset-workflow runs that require run-record persistence and MySQL verification. Do not use for bounded non-persistent product-discovery experiments, code fixes, or run review.

  • Lowcode ai run review

    xylvvv/agent-skills/skills/lowcode-ai-run-review Skill

    no license0★ repo

    Review lowcode AI real-chain run records, classify import/evaluation/manual issues, and decide whether to observe, analyze, implement, validate, or route to frontend product follow-up. Not for spec generation or code editing.

  • Plantuml check

    xylvvv/agent-skills/skills/plantuml-check Skill

    no license0★ repo

    Use when validating, syntax-checking, or optionally rendering PlantUML .puml files, especially before claiming generated diagrams are valid or when another skill produces PlantUML artifacts.

  • Git workflow

    mabyko/AgentSkills/skills/git-workflow Skill

    0★ repo

    Use when choosing or executing Git-only workflows: branching, staging, commits, signed commits, DCO sign-off, local merge/rebase/squash, conflicts, tags, stashes, reflog recovery, branch cleanup, Git safety checks, or Git-history release prep.

  • Vibe check

    holzerjm/SkillsDemo/Claude/vibe-check Skill

    0★ repo

    Generate a fun, visual "vibe check" report for any topic, company, product, or event. Creates an entertaining analysis with ratings, emoji verdicts, and pop culture references. Use when someone says "vibe check" or asks for a fun/casual analysis.

  • Vibe check

    holzerjm/SkillsDemo/Cursor/vibe-check Skill

    0★ repo

    Generate a fun, visual "vibe check" report for any topic, company, product, or event. Creates an entertaining analysis with ratings, emoji verdicts, and pop culture references. Use when someone says "vibe check" or asks for a fun/casual analysis.

  • Cm expert

    holzerjm/SkillsDemo/cm-expert Skill

    0★ repo

    Generate a fun, visual "vibe check" report for any topic, company, product, or event. Creates an entertaining analysis with ratings, emoji verdicts, and pop culture references. Use when someone says "vibe check" or asks for a fun/casual analysis.

  • Impeccable

    BAKUGOS1/SkilledAgents-Toolkit/plugins/skilled-agents/skills/impeccable Skill

    0★ repo

    Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

    The same file is in 4 other repositories

  • Lint and validate

    BAKUGOS1/SkilledAgents-Toolkit/plugins/skilled-agents/skills/lint-and-validate Skill

    0★ repo

    MANDATORY: Run validation after EVERY code change. No task is done until the code is error-free.

  • Impeccable

    BAKUGOS1/SkilledAgents-Toolkit/skills/codex/impeccable Skill

    0★ repo

    Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

    The same file is in 4 other repositories

  • Lint and validate

    BAKUGOS1/SkilledAgents-Toolkit/skills/projects/wrkly/lint-and-validate Skill

    0★ repo

    MANDATORY: Run validation after EVERY code change. No task is done until the code is error-free.

  • New project

    AGilbertDev/agilbertdev-recipes/skills/new-project Skill

    no license0★ repo

    AGilbertDev's playbook for starting a new personal project. Scaffolds a Nuxt app, wires in the agilbertdev-recipes submodule, and sets the shared Bun, ESLint, Prettier, husky, and i18n baseline. Use when creating a new repo or bootstrapping a project from scratch.

  • Verification first workflow

    w3rdist-creator/agent-intelligence-economy/skills/verification-first-workflow Skill

    0★ repo

    Run deterministic checks before claiming success or asking another model to opine.

  • Create verification strategy

    qa-veritas/skillpack/skills/create_verification_strategy Skill

    0★ repo

    Given an intended change, define the pre-check, the observable post-checks that prove it worked, and the signal that triggers rollback. Use before applying any change to a live resource.

  • Pre push compliance

    thegeekybeng/architecture-governance/skills/pre-push-compliance Skill

    0★ repo

    Enforce a mandatory pre-push audit checking CI/CD, Actions Workflow, Runtime/Package Manager, and README configurations. This skill ONLY allows Git push execution if all checks PASS. Triggers: "pre-push audit", "verify pre-push compliance", "push to main with audit", "git push with audit".

  • Adversarial review

    selamy-labs/agent-skills/skills/adversarial-review Skill

    0★ repo

    Use before claiming a high-stakes artifact done, verified, or merged. Have an independent grader adversarially review it — prompted to refute and find reasons not to ship, not to bless — and iterate to an explicit ship-or-revise verdict.

  • Exhaustive match

    selamy-labs/agent-skills/skills/exhaustive-match Skill

    0★ repo

    Use when every known variant must be handled. Prefer compiler, type-checker, linter, or test-enforced exhaustive matches.

  • Live state verification

    selamy-labs/agent-skills/skills/live-state-verification Skill

    0★ repo

    Use when verifying service health, deployed state, cluster objects, credentials, or automation results where the wrong auth context can produce false empty results.

  • Merge conflict discipline

    selamy-labs/agent-skills/skills/merge-conflict-discipline Skill

    0★ repo

    Resolve merge conflicts by intent (never blind accept-ours/theirs) AND prevent them structurally — integrate, never clobber.

  • Steelman then critique

    selamy-labs/agent-skills/skills/steelman-then-critique Skill

    0★ repo

    Use when critiquing a proposal, design, or argument. First state its strongest form — the best honest case for it — then critique that, so the critique actually lands instead of knocking down a weak version or rubber-stamping a flawed one.

  • Verify delegated work

    selamy-labs/agent-skills/skills/verify-delegated-work Skill

    0★ repo

    Use when accepting, merging, or building on work produced by a sub-agent, delegated worker, or any process you did not run yourself. A worker's done, idle, or green-CI signal is a claim, not proof — independently verify the real artifact first.

  • Verify from system of record

    selamy-labs/agent-skills/skills/verify-from-system-of-record Skill

    0★ repo

    Absence of visibility is not absence of the thing — verify state, identity, and existence against the system of record, not a partial or cached view.

  • Verify real artifact

    selamy-labs/agent-skills/skills/verify-real-artifact Skill

    0★ repo

    Use when validating whether a send, deploy, workflow, document, trace, or product flow really landed or works. Focuses verification on the real artifact instead of logs or indirect proxies.

  • Oversized description

    selamy-labs/agent-skills/tests/fixtures/oversized-description Skill

    0★ repo

    This is a very long description that contains way too many words and should be rejected by the validator because it exceeds the forty five word limit that is enforced by the naming lint checker which ensures skill descriptions stay concise and readable for humans and machines alike without unnecessary verbosity or padding

  • Setup indexing

    Myra-Agents/skills/skills/setup-indexing Skill

    0★ repo

    Install a greppable code index so agents locate files/symbols without rescanning the project every session — generates an index.sh (dirs/files/symbols with file:line, per repo or workspace member), wires .gitignore + CLAUDE.md, offers a SessionStart refresh hook, then runs a validation pipeline (syntax, edge-case sandbox, measured recall check, staleness detection, optional A/B benchmark). Use whenever the user wants to set up code indexing, complains that the agent re-scans/re-explores the whole project to find things, asks to make agent search faster/cheaper, or mentions a project index, code map, symbol index, or ctags-like setup for agents.

  • Commit

    shuymn/skills/skills/commit Skill

    no license0★ repo

    Creates meaningful git commits by analyzing changes and committing in logical units. Use when the user wants to commit changes to git, requests commit creation, or asks to save changes to version control. Supports --english and --japanese for commit language selection and --branch to create a new branch before committing.

  • Create pr

    shuymn/skills/skills/create-pr Skill

    no license0★ repo

    Reviews committed changes and creates a pull request on GitHub. Use when the user wants to create a PR, push changes for review, or open a pull request. Requires a GitHub repository. Supports --japanese flag for Japanese descriptions, --base flag to specify target branch, and --update flag to update an existing PR.

  • Proofread

    shuymn/skills/skills/proofread Skill

    no license0★ repo

    Review text for AI writing tropes and mechanical prose patterns, then report findings with concrete rewrite suggestions. Use when the user asks to proofread, lint, or polish writing — especially docs, blog posts, READMEs, commit messages, PR descriptions, or any prose that should read as human-written. Also use when the user says "check for AI slop", "does this sound like AI", "make this sound more natural", or wants to de-AI their text.

  • Triage review

    shuymn/skills/skills/triage-review Skill

    no license0★ repo

    Processes AI reviewer feedback and applies only verified fixes. Works in two modes: (1) fetches comments from a PR URL or current branch, (2) processes feedback pasted directly into the conversation. Trigger when the user wants to bulk-process or apply AI review suggestions — from a GitHub PR or pasted text. Do NOT trigger for single questions about what a bot said, or general code review discussion.

  • Si confidence source

    jpoindexter/self-insight-agent-skills/skills/si-confidence-source Skill

    0★ repo

    Audit WHY something feels right before trusting the feeling. Three false cues — fluency (easy to generate), pseudorelevance (knowing a lot around the topic), and inherited self-view ("I'm good at this") — produce confidence unconnected to accuracy. Name the cue; if it's one of these, downgrade and verify. Use whenever a confident answer arrives without an explicit check.

    The same file is in 1 other repository

  • Si corrective feedback

    jpoindexter/self-insight-agent-skills/skills/si-corrective-feedback Skill

    0★ repo

    Feedback is the riskiest thing you do — nearly 40% of feedback interventions make performance WORSE. The difference is altitude: criticism aimed at the task and the next concrete step helps; criticism aimed at the author's worth triggers self-protection and backfires. Attack the code, name the fix, frame the gap as closable. Use when you critique code, review a sub-agent's output, or push back on a user's plan.

  • Si egocentric check

    jpoindexter/self-insight-agent-skills/skills/si-egocentric-check Skill

    0★ repo

    You overweight your own frame and forget the other party — the user, another system, the competing process — operates under the same constraints you do. Before any comparative, "this is better/unique/special," or controllability claim, explicitly model the other side. Use on relative judgments, uniqueness claims, and estimates of how much you control an outcome.

    The same file is in 1 other repository

  • Software delivery workflow

    percymcn/agent-cookbook/skills/software-development/software-delivery-workflow Skill

    0★ repo

    Software delivery workflow umbrella: planning, spikes/prototypes, test-driven development, systematic debugging, debugger use, and pre-commit code review/verification. Use for class-level engineering process guidance before or during code changes.

  • Commit messages

    andersonoliveiraventurini/esquadrao-classe-a/.agents/skills/claude-code-mastery/reference/skills/commit-messages Skill

    no license0★ repo

    Generate clear, conventional commit messages from git diffs. Use when writing commit messages, reviewing staged changes, or preparing releases.

    The same file is in 3 other repositories

  • Commit messages

    andersonoliveiraventurini/esquadrao-classe-a/claude-code-mastery/skills/claude-code-mastery/reference/skills/commit-messages Skill

    no license0★ repo

    Generate clear, conventional commit messages from git diffs. Use when writing commit messages, reviewing staged changes, or preparing releases.

  • Commit messages

    andersonoliveiraventurini/esquadrao-classe-a/esquadrao-completo/skills/claude-code-mastery/reference/skills/commit-messages Skill

    no license0★ repo

    Generate clear, conventional commit messages from git diffs. Use when writing commit messages, reviewing staged changes, or preparing releases.

  • Cdk three source drift check

    esaldgut/ai-native-engineering-workspace/global-skills/aws-go/cdk-three-source-drift-check Skill

    0★ repo

    Before a CDK deploy that touches an already-deployed stack, cross-check three sources, not one: cdk synth (what your code says should exist), cdk diff (synth vs the last-deployed template), and cdk drift (the deployed template vs live AWS reality). cdk diff is BLIND to manual console/CLI changes — it only compares templates, never live state; cdk drift (CDK CLI 2.1017.0+, May 2025) calls CloudFormation drift detection to catch them. Note that not all resource types support drift detection (status NOT_CHECKED), so keep an aws cli describe fallback for those. Use when planning a CDK deploy onto live stacks (IAM, Lambda env, EventBridge rules, API Gateway, Cognito triggers).

  • Verify provider api supports property

    esaldgut/ai-native-engineering-workspace/global-skills/aws-go/verify-provider-api-supports-property Skill

    0★ repo

    Before a design doc promises an architectural property — reversibility, idempotency, exactly-once, cross-service atomicity, mechanical compensation, a sub-Xms SLA — verify the concrete AWS SDK method that mechanically guarantees it actually exists and supports the claim. "The Saga from the book" is not the same as "a Saga implementable on Cognito + Step Functions." AWS's own Saga docs admit the pattern gives eventual consistency, not ACID. For each promised property, demand the specific AWS API that backs it; if none exists, the property is NOT the system's and must be documented as "not mechanically guaranteed" or the design must change. Use at design review, whenever a doc claims a strong distributed-systems guarantee.

  • Android build sync

    esaldgut/ai-native-engineering-workspace/global-skills/claude-code-workflow/android-build-sync Skill

    0★ repo

    One-command Android build-consistency gate, environment-agnostic — format (ktlint via org.jlleitschuh.gradle.ktlint), static analysis (detekt via io.gitlab.arturbosch.detekt, with the Compose ruleset), platform lint (./gradlew lintDebug), then compile/package (./gradlew assembleDebug), with pre-flight checks for JDK (17/21) and the Gradle wrapper. Enforces ./gradlew over system gradle, a detekt baseline for retrofitting, and parallel+caching gradle.properties. Use to set up or run a pre-commit/pre-push/CI build gate for a Kotlin/Compose project. No hardcoded machine paths.

  • Cli build sync pipeline

    esaldgut/ai-native-engineering-workspace/global-skills/claude-code-workflow/cli-build-sync-pipeline Skill

    0★ repo

    Run a platform-agnostic project-consistency pass before a commit/PR — regenerate the project file, format, lint, build, then take an IDE second opinion via the editor's MCP server to catch diagnostics the CLI build truncates or never emits. Works for Xcode, Gradle, Node, Go, etc. Uses Claude Code's PostToolUse hook (format-on-write) and the IDE-Navigator check (e.g. Xcode's XcodeListNavigatorIssues) as a complement to the build log. Use before declaring a change ready, on /sync, or when wiring format/lint/build automation. Generic cross-platform version; an Android-specific build-sync variant exists separately.

  • Skill extraction pattern

    esaldgut/ai-native-engineering-workspace/global-skills/meta/skill-extraction-pattern Skill

    0★ repo

    Extract public, reusable Agent Skills from a corpus of private, NDA-locked project skills. Seven-step pipeline — inventory, classify, research-verify, rewrite-from-scratch, re-classify, anchor-with-a-concrete-example, self-applicability check — that strips the secret architecture and business context while keeping the reusable pattern. Use when you want to publish (open-source, portfolio, share) skills you built inside a confidential codebase without leaking the client's stack.

  • Code review maintenance

    Nick2bad4u/codex-skills/skills/code-review-maintenance Skill

    no license0★ repo

    Maintains code-review quality across repos, files, configs, and low-confidence claims. Use when reviewing codebases/files, brittle implementations, consistency drift, comment triage, correctness, maintainability, security, release, or test risks.

  • Dependency update maintenance

    Nick2bad4u/codex-skills/skills/dependency-update-maintenance Skill

    no license0★ repo

    Personal multi-skill repository for reusable Codex workflows.

  • Eslint plugin maintenance

    Nick2bad4u/codex-skills/skills/eslint-plugin-maintenance Skill

    no license0★ repo

    Builds, audits, and maintains ESLint plugin repos. Use when scaffolding plugins, auditing best practices, syncing rule docs/tests/presets/generated surfaces, or discovering and implementing high-value net-new ESLint rules.

  • Lint cleanup

    Nick2bad4u/codex-skills/skills/lint-cleanup Skill

    no license0★ repo

    Validates and repairs lint, ESLint, and static-analysis diagnostics at the root cause. Use when running lint, resolving errors/warnings, removing unnecessary disable comments, or replacing suppressions with code, type, config, or test fixes.

  • Prettier plugin maintenance

    Nick2bad4u/codex-skills/skills/prettier-plugin-maintenance Skill

    no license0★ repo

    Builds, audits, and maintains Prettier plugin and shared config repos. Use when scaffolding plugins, fixing parsers/printers/options, auditing doc-builder behavior, testing formatting output, or validating package/editor/CI integration.

  • Python strict development

    Nick2bad4u/codex-skills/skills/python-strict-development Skill

    no license0★ repo

    Maintains strict Python projects with Ruff, mypy, Pyright, pytest, editor, and package-script gates. Use when creating, auditing, or repairing strict lint, format, typecheck, test, compile, or VS Code tooling practices.

  • Source verify

    frankxai/marine-agent-skills/skills/source-verify Skill

    0★ repo

    Use to verify every factual claim in a Blue Life Commons draft is backed by an acceptable source before PR. Defends against AI-generated text drifting from cited fact. Triggers — "verify sources", "check citations", "is every claim sourced".

  • Eval loops

    K-9Nine/skipthespec/eval-loops Skill

    0★ repo

    Design, build, run, and maintain automated test and evaluation loops so Claude can verify its own work without deploying to users. Use when the user says 'eval loop', 'set up evals', 'test harness', 'automated testing', 'how do I know it works', 'regression suite', 'grade the agent', or when a build needs a verification net. Implements Anthropic's evals method: 20-50 tasks from real failures, deterministic graders + LLM-as-judge, grade outcomes not paths, isolated trials, pass@k vs pass^k, read the transcripts. The safety net under autonomous-build and the quality gate before dogfood-loop promotion. Load autonomous-dev first.

  • Dingtang okr review

    stardustai/stardust-skills/skills/dingtang-okr-review Skill

    0★ repo

    Use when the user asks to export, review, audit, score, or summarize 叮当OKR/Dingdang OKR objectives, KR progress, CEO OKR review, people progress reports, Q2/Q3/Q4 OKR data, or asks to organize OKR data into Excel and evaluate KR completion with evidence.

  • Mt weekly review

    MeisterLabs/meister-mcp-skills/skills/mt-weekly-review Skill

    0★ repo

    Surface overdue tasks, tasks due this week, and recently completed tasks across MeisterTask projects for a weekly review.